nat9dai's picture
First Push
7197a76 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7491956353187561,
"min": 0.7491956353187561,
"max": 2.8545963764190674,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7120.35546875,
"min": 7120.35546875,
"max": 29139.720703125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.679999351501465,
"min": 0.29300457239151,
"max": 12.679999351501465,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2472.599853515625,
"min": 56.84288787841797,
"max": 2566.025634765625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06897381325011248,
"min": 0.06220848680029889,
"max": 0.07445942270650824,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2758952530004499,
"min": 0.2539795283570557,
"max": 0.3639906430594148,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22813809706884275,
"min": 0.1387611513834118,
"max": 0.28710337216947596,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.912552388275371,
"min": 0.5550446055336472,
"max": 1.3182429250548866,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.204545454545453,
"min": 3.522727272727273,
"max": 25.204545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 155.0,
"max": 1369.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.522727272727273,
"max": 25.204545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 155.0,
"max": 1369.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1761545721",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1761546149"
},
"total": 427.2898558269999,
"count": 1,
"self": 0.43338253299975804,
"children": {
"run_training.setup": {
"total": 0.026437068000063846,
"count": 1,
"self": 0.026437068000063846
},
"TrainerController.start_learning": {
"total": 426.83003622600006,
"count": 1,
"self": 0.3331915770111209,
"children": {
"TrainerController._reset_env": {
"total": 3.048234037000043,
"count": 1,
"self": 3.048234037000043
},
"TrainerController.advance": {
"total": 423.37374709598885,
"count": 18192,
"self": 0.3572094269752597,
"children": {
"env_step": {
"total": 305.8534866190083,
"count": 18192,
"self": 238.9423320240012,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.7114923209923,
"count": 18192,
"self": 1.2322232949907175,
"children": {
"TorchPolicy.evaluate": {
"total": 65.47926902600159,
"count": 18192,
"self": 65.47926902600159
}
}
},
"workers": {
"total": 0.19966227401482683,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 425.0433828119682,
"count": 18192,
"is_parallel": true,
"self": 214.78537371396078,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005410457999914797,
"count": 1,
"is_parallel": true,
"self": 0.004083482999817534,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013269750000972635,
"count": 10,
"is_parallel": true,
"self": 0.0013269750000972635
}
}
},
"UnityEnvironment.step": {
"total": 0.03457857899991268,
"count": 1,
"is_parallel": true,
"self": 0.0005607859999372522,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040035600000010163,
"count": 1,
"is_parallel": true,
"self": 0.00040035600000010163
},
"communicator.exchange": {
"total": 0.03177280199997767,
"count": 1,
"is_parallel": true,
"self": 0.03177280199997767
},
"steps_from_proto": {
"total": 0.001844634999997652,
"count": 1,
"is_parallel": true,
"self": 0.00034885999980360793,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001495775000194044,
"count": 10,
"is_parallel": true,
"self": 0.001495775000194044
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 210.2580090980074,
"count": 18191,
"is_parallel": true,
"self": 10.059121497013052,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.304017478999981,
"count": 18191,
"is_parallel": true,
"self": 5.304017478999981
},
"communicator.exchange": {
"total": 159.641166941003,
"count": 18191,
"is_parallel": true,
"self": 159.641166941003
},
"steps_from_proto": {
"total": 35.25370318099135,
"count": 18191,
"is_parallel": true,
"self": 6.381962524011101,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.87174065698025,
"count": 181910,
"is_parallel": true,
"self": 28.87174065698025
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 117.16305105000527,
"count": 18192,
"self": 0.3954749480137707,
"children": {
"process_trajectory": {
"total": 26.09888324699068,
"count": 18192,
"self": 25.58803702299076,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5108462239999199,
"count": 4,
"self": 0.5108462239999199
}
}
},
"_update_policy": {
"total": 90.66869285500081,
"count": 90,
"self": 36.73906085499618,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.92963200000463,
"count": 4587,
"self": 53.92963200000463
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.639999578008428e-07,
"count": 1,
"self": 8.639999578008428e-07
},
"TrainerController._save_models": {
"total": 0.07486265200009257,
"count": 1,
"self": 0.0007161760001963557,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07414647599989621,
"count": 1,
"self": 0.07414647599989621
}
}
}
}
}
}
}